41:I[185,["/_next/static/chunks/3xnt26d00_zk-.js","/_next/static/chunks/2aeejfufo02km.js","/_next/static/chunks/42spz6paskvb6.js","/_next/static/chunks/06x30xgfe6iur.js","/_next/static/chunks/2qm8z4gyuajgj.js","/_next/static/chunks/3jnlvw-emqotx.js"],"SendEmailButton"] 43:I[63625,["/_next/static/chunks/3xnt26d00_zk-.js","/_next/static/chunks/2aeejfufo02km.js","/_next/static/chunks/42spz6paskvb6.js","/_next/static/chunks/06x30xgfe6iur.js","/_next/static/chunks/2qm8z4gyuajgj.js","/_next/static/chunks/3jnlvw-emqotx.js"],"AddToLibraryButton"] 44:I[29721,["/_next/static/chunks/3xnt26d00_zk-.js","/_next/static/chunks/2aeejfufo02km.js","/_next/static/chunks/42spz6paskvb6.js","/_next/static/chunks/06x30xgfe6iur.js","/_next/static/chunks/2qm8z4gyuajgj.js","/_next/static/chunks/3jnlvw-emqotx.js"],"ShareButton"] 45:I[58016,["/_next/static/chunks/3xnt26d00_zk-.js","/_next/static/chunks/2aeejfufo02km.js","/_next/static/chunks/42spz6paskvb6.js","/_next/static/chunks/06x30xgfe6iur.js","/_next/static/chunks/2qm8z4gyuajgj.js","/_next/static/chunks/3jnlvw-emqotx.js"],"ProcessEpisodeButton"] 46:I[45269,["/_next/static/chunks/3xnt26d00_zk-.js","/_next/static/chunks/2aeejfufo02km.js","/_next/static/chunks/42spz6paskvb6.js","/_next/static/chunks/06x30xgfe6iur.js","/_next/static/chunks/2qm8z4gyuajgj.js","/_next/static/chunks/3jnlvw-emqotx.js"],"SignupCTA"] 3a:["$","div",null,{"className":"flex flex-wrap items-center gap-x-4 gap-y-1 font-mono text-[12px] uppercase tracking-[0.1em] text-[color:var(--fg-3)]","children":[["$","time",null,{"dateTime":"2026-07-15T17:57:02.000Z","children":"July 15, 2026"}],["$","span",null,{"aria-hidden":true,"children":"·"}],["$","span",null,{"children":"00:01:17"}],false]}] 3b:["$","p",null,{"className":"max-w-[60ch] text-[18px] leading-[1.5] text-[color:var(--fg-2)]","children":"CNBC reports Apple is exploring a startup's model compression to run AI on iPhones, raising cost and privacy questions."}] 42:T429,

CNBC reported that Apple is in talks with a startup that specializes in compressing AI models to run on iPhones. The move aligns with Apple's strategy to execute more AI locally, reducing reliance on cloud infrastructure and lowering latency. On-device AI relies on techniques such as quantization, pruning, and distillation to fit models within CPU, GPU, and Neural Engine limits. The shift could reduce cloud inference costs that depend on GPUs from providers like Amazon Web Services, Microsoft Azure, and Google Cloud. Competitors including Google, Samsung, Qualcomm, and Meta are advancing on-device AI capabilities. Founders should benchmark compact models, assess battery impact, and decide which features should run locally versus in the cloud.

Learn more on this news by visiting us at: https://greyjournal.net/news/

Hosted on Acast. See acast.com/privacy for more information.